A system and method for mitigating audio feedback may calculate a smoothed frequency spectrum of an audio signal. Previously detected candidate feedback tones may be obtained. Candidate feedback tones may be determined responsive to a frequency spectrum of the audio signal, the smoothed frequency spectrum and the previously detected candidate feedback tones. One or more signal characteristics associated with the audio signal and feedback coefficients associated with the candidate feedback tones may be obtained. The feedback coefficients may be modified responsive to the one or more signal characteristics. Actionable feedback tones may be determined responsive to the associated feedback coefficients exceeding a respective feedback threshold. Feedback suppression coefficients associated with each of the determined actionable feedback tones may be generated and may be utilized to suppress the actionable feedback tones.

An electronic device, an echo signal cancelling method thereof and a non-transitory computer readable recording medium is provided. The electronic device according to an exemplary embodiment includes a speaker configured to output a sound corresponding to a reference signal, a microphone configured to generate a microphone signal by obtaining a received sound, and a filter configured to cancel an echo signal of the reference signal from the microphone signal. In addition, the filter includes a first filter configured to estimate an echo signal of the reference signal and cancel the estimated echo signal from the microphone signal, and a second filter configured to generate an adaptive gain to cancel a residual echo from the microphone signal in which the estimated echo signal is canceled, and generate an output signal by using the generated adaptive gain and the microphone signal in which the estimated echo signal is canceled.

Embodiments disclosed herein may include a wearable apparatus including a frame having a memory and processor associated therewith. The apparatus may include a camera associated with the frame and in communication with the processor, the camera configured to track an eye of a wearer. The apparatus may also include at least one microphone associated with the frame. The at least one microphone may be configured to receive a directional instruction from the processor. The directional instruction may be based upon an adaptive beamforming analysis performed in response to a detected eye movement from the infrared camera. The apparatus may also include a speaker associated with the frame configured to provide an audio signal received at the at least one microphone to the wearer.

A speech signal processing method is performed at a terminal device, including: obtaining a recorded signal and a to-be-output speech signal, the recorded signal including a noise signal and an echo signal; calculating a loop transfer function according to the recorded signal and the speech signal; calculating a power spectrum of the echo signal and a power spectrum of the noise signal according to the recorded signal, the speech signal, and the loop transfer function; calculating a frequency weighted coefficient according to the two power spectra of the echo signal and the noise signal; adjusting a frequency amplitude of the speech signal based on the frequency weighted coefficient; and outputting the adjusted speech signal to a speaker electrically coupled to the terminal device. As such, the frequency amplitude of the speech signal is automatically adjusted according to the relative frequency distribution of a noise signal and the speech signal.

In an example, an audio system, which may comprise an integrated circuit, comprises an amplifier and a combiner. The amplifier is configured to output a first amplified audio signal to a speaker. The combiner is configured to: receive the first amplified audio signal from the amplifier, receive a second audio signal, combine the first amplified audio signal and second audio signal into a combined signal, and output the combined signal.

Provided are an audio signal processing method, a training method, an apparatus and a storage medium, relating to the field of data processing, in particular to, the field of voice. The audio signal processing method includes: eliminating at least part of a linear echo signal from a mixed voice signal, to obtain an intermediate processing signal, where the mixed voice signal is obtained by mixing a target voice signal with an echo signal, and the echo signal is generated in an environment where the target voice signal is located and includes the linear echo signal and a nonlinear echo signal; and removing the nonlinear echo signal and a residual part of the linear echo signal from the intermediate processing signal, by using a target full convolution neural network model, to obtain an approximate target voice signal, the target full convolution neural network model including at least two convolution layers.

Example techniques involve systems with multiple acoustic echo cancellers. An example implementation captures first audio within an acoustic environment and detecting, within the captured first audio content, a wake-word. In response to the wake-word and before playing an acknowledgement tone, the implementation activates (a) a first sound canceller when one or more speakers are playing back audio content or (b) a second sound canceller when the one or more speakers are idle. In response to the wake-word and after activating either (a) the first sound canceller or (b) the second sound canceller, the implementation outputs the acknowledgement tone via the one or more speakers. The implementation captures second audio within the acoustic environment and cancelling the acoustic echo of the acknowledgement tone from the captured second audio using the activated sound canceller.

Apparatus, methods and computer programs are provided for reducing echo in microphone signals. The apparatus can be configured to obtain an echo path delay estimate and obtain information indicative of a number of future frames used by an acoustic echo cancellation filter. The apparatus can also be configured to obtain information indicative of a time shift between consecutive frames processed by the acoustic echo cancellation filter. The apparatus can also be configured to determine at least a first delay to be added to a loudspeaker signal and determine at least a second delay to be added to a microphone signal. The determination of the first delay and the second delay is based on the echo path delay estimate, the number of future frames and the time shift between consecutive frames processed by the acoustic echo cancellation filter.

Techniques for adaptively providing acoustic echo cancellation (AEC) for a stereo audio signal associated with at least one microphone are discussed herein. Some embodiments may include determining, based at least in part on detecting a reference signal associated with a channel sample portion of the stereo audio signal, a panning state of the stereo audio signal. A hard-panned-configured AEC processing filter or a soft-panned-configured AEC processing filter is applied to the stereo audio signal to generate a filtered audio signal output based on the panning state.

A method for signal processing, receiving a time domain signal having a sample-rate Fs and generating N time domain signal bands, each having a bandwidth equal to Fs/N. Receiving the N signal bands and transforming a first time domain signal band to a frequency domain at a first resolution and a second time domain signal band to the frequency domain at a second resolution, where the first resolution may be different from the second resolution. Determining one or more first filter coefficients using the frequency domain components from the first signal band and one or more second filter coefficients using the frequency domain components from the second signal band. Transforming the first and second filter coefficients from the frequency domain to a time domain. Applying the first and second time domain filter coefficients to the first and second time domain signals, respectively.